[PATCH bpf-next v2 3/6] libbpf: Create a bpf_link in bpf_map__attach_struct_ops().

[Kui-Feng Lee <kuifeng@meta.com>]

bpf_map__attach_struct_ops() was creating a dummy bpf_link as a
placeholder, but now it is constructing an authentic one by calling
bpf_link_create() if the map has the BPF_F_LINK flag.

You can flag a struct_ops map with BPF_F_LINK by calling
bpf_map__set_map_flags().

Signed-off-by: Kui-Feng Lee <kuifeng@meta.com>
---
 tools/lib/bpf/bpf.c    |  2 +
 tools/lib/bpf/libbpf.c | 84 ++++++++++++++++++++++++++++++++----------
 2 files changed, 66 insertions(+), 20 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9aff98f42a3d..6e270bb95ab7 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -731,6 +731,8 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, tracing))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_STRUCT_OPS:
+		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 35a698eb825d..40f239cd1150 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -115,6 +115,7 @@ static const char * const attach_type_name[] = {
 	[BPF_SK_REUSEPORT_SELECT_OR_MIGRATE]	= "sk_reuseport_select_or_migrate",
 	[BPF_PERF_EVENT]		= "perf_event",
 	[BPF_TRACE_KPROBE_MULTI]	= "trace_kprobe_multi",
+	[BPF_STRUCT_OPS]		= "struct_ops",
 };
 
 static const char * const link_type_name[] = {
@@ -7677,6 +7678,26 @@ static int bpf_object__resolve_externs(struct bpf_object *obj,
 	return 0;
 }
 
+static void bpf_map_prepare_vdata(const struct bpf_map *map)
+{
+	struct bpf_struct_ops *st_ops;
+	__u32 i;
+
+	st_ops = map->st_ops;
+	for (i = 0; i < btf_vlen(st_ops->type); i++) {
+		struct bpf_program *prog = st_ops->progs[i];
+		void *kern_data;
+		int prog_fd;
+
+		if (!prog)
+			continue;
+
+		prog_fd = bpf_program__fd(prog);
+		kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i];
+		*(unsigned long *)kern_data = prog_fd;
+	}
+}
+
 static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path)
 {
 	int err, i;
@@ -7728,6 +7749,10 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 	btf__free(obj->btf_vmlinux);
 	obj->btf_vmlinux = NULL;
 
+	for (i = 0; i < obj->nr_maps; i++)
+		if (bpf_map__is_struct_ops(&obj->maps[i]))
+			bpf_map_prepare_vdata(&obj->maps[i]);
+
 	obj->loaded = true; /* doesn't matter if successfully or not */
 
 	if (err)
@@ -11429,11 +11454,29 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 	return link;
 }
 
+struct bpf_link_struct_ops {
+	struct bpf_link link;
+	int map_fd;
+};
+
 static int bpf_link__detach_struct_ops(struct bpf_link *link)
 {
+	struct bpf_link_struct_ops *st_link;
 	__u32 zero = 0;
 
-	if (bpf_map_delete_elem(link->fd, &zero))
+	st_link = container_of(link, struct bpf_link_struct_ops, link);
+
+	if (st_link->map_fd < 0) {
+		/* Fake bpf_link */
+		if (bpf_map_delete_elem(link->fd, &zero))
+			return -errno;
+		return 0;
+	}
+
+	if (bpf_map_delete_elem(st_link->map_fd, &zero))
+		return -errno;
+
+	if (close(link->fd))
 		return -errno;
 
 	return 0;
@@ -11441,10 +11484,9 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link)
 
 struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map)
 {
-	struct bpf_struct_ops *st_ops;
-	struct bpf_link *link;
-	__u32 i, zero = 0;
-	int err;
+	struct bpf_link_struct_ops *link;
+	__u32 zero = 0;
+	int err, fd;
 
 	if (!bpf_map__is_struct_ops(map) || map->fd == -1)
 		return libbpf_err_ptr(-EINVAL);
@@ -11453,31 +11495,33 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map)
 	if (!link)
 		return libbpf_err_ptr(-EINVAL);
 
-	st_ops = map->st_ops;
-	for (i = 0; i < btf_vlen(st_ops->type); i++) {
-		struct bpf_program *prog = st_ops->progs[i];
-		void *kern_data;
-		int prog_fd;
+	err = bpf_map_update_elem(map->fd, &zero, map->st_ops->kern_vdata, 0);
+	if (err) {
+		err = -errno;
+		free(link);
+		return libbpf_err_ptr(err);
+	}
 
-		if (!prog)
-			continue;
+	link->link.detach = bpf_link__detach_struct_ops;
 
-		prog_fd = bpf_program__fd(prog);
-		kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i];
-		*(unsigned long *)kern_data = prog_fd;
+	if (!(map->def.map_flags & BPF_F_LINK)) {
+		/* Fake bpf_link */
+		link->link.fd = map->fd;
+		link->map_fd = -1;
+		return &link->link;
 	}
 
-	err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0);
-	if (err) {
+	fd = bpf_link_create(map->fd, -1, BPF_STRUCT_OPS, NULL);
+	if (fd < 0) {
 		err = -errno;
 		free(link);
 		return libbpf_err_ptr(err);
 	}
 
-	link->detach = bpf_link__detach_struct_ops;
-	link->fd = map->fd;
+	link->link.fd = fd;
+	link->map_fd = map->fd;
 
-	return link;
+	return &link->link;
 }
 
 typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr,
-- 
2.30.2